Giovanni De Toni
PhD Student, Machine Learning
Mobile and Social Computing Lab, Fondazione Bruno Kessler
Structured Machine Learning Group, University of Trento
European Laboratory for Learning and Intelligent Systems (ELLIS)


I am a PhD student at Fondazione Bruno Kessler (FBK) and European Laboratory for Learning and Intelligent Systems (ELLIS), under the supervision of Bruno Lepri (FBK), Andrea Passerini (University of Trento) and Manuel Gomez Rodriguez (Max Planck Institute for Software Systems). My research interests relate to trustworthy and explainable AI topics, focusing on algorithmic recourse, causality, counterfactual explanations and user-aware decision making systems.

During my PhD, I also spent a visiting period at the Max Planck Institute for Software Systems (Germany) and I interned at X, the moonshot factory (Google X) (Mountain View, CA) where I worked on Large Language Models (LLMs) applied to program synthesis supervised by Dr. Rishabh Singh.


Before the PhD, I was a Research Scientist at VUI, Inc., a Boston's startup building innovative conversational agents and a Research Assistant in the Structured Machine Learning Group (SML) at the University of Trento, Italy.

During my undergraduate studies, I interned at CERN (2019), and I spent a semester at the University of Edinburgh (2018) as an Erasmus student. I also participated in the Google Summer of Code (2017) as a Software Developer for Shogun, a machine learning library. I received my Bachelor and Master's degree (cum laude) from the University of Trento in 2017 and 2020 respectively. I also obtained a scholarship for my academic performance through my undergraduate studies.


Latest News

Publications & Preprints

  1. Time Can Invalidate Algorithmic Recourse
    Giovanni De Toni, Stefano Testo, Bruno Lepri, Andrea Passerini
    Preprint (2024)
    [paper][code]

  2. Towards Human-AI Complementarity with Predictions Sets
    Giovanni De Toni, Nastaran Okati, Suhas Thejaswi, Eleni Straitouri, Manuel Gomez-Rodriguez
    NeurIPS (2024)
    [paper][code]

  3. Preference Elicitation in Interactive and User-centered Algorithmic Recourse: an Initial Exploration
    Seyedehdelaram Esfahani, Giovanni De Toni, Bruno Lepri, Andrea Passerini, Katya Tentori, Massimo Zancanaro
    ACM UMAP (2024)
    Best Short Paper Runner-up at the 32nd ACM UMAP Conference (2024)
    [paper][code (will be available soon)]

  4. Personalized Algorithmic Recourse with Preference Elicitation
    Giovanni De Toni, Paolo Viappiani, Stefano Teso, Bruno Lepri, Andrea Passerini
    Transactions on Machine Learning Research (2024)
    [paper][code]
    A preliminary version of this work was accepted at the at NeurIPS 2022 workshop on Human in the Loop Learning (HILL).
    See here for the previous paper.

  5. Synthesizing explainable counterfactual policies for algorithmic recourse with program synthesis
    Giovanni De Toni, Bruno Lepri, Andrea Passerini
    Machine Learning (2023)
    [paper][code]

  6. Learning compositional programs with arguments and sampling
    Giovanni De Toni, Luca Erculiani, Andrea Passerini
    Advances in Programming Languages and Neurosymbolic Systems (AIPLANS), NeurIPS, 2021.
    10th International Workshop on Statistical Relational AI (StarAI), IJCLR, 2021.
    [paper][code][poster]

  7. A general method for estimating the prevalence of Influenza-Like-Symptoms with Wikipedia data
    Giovanni De Toni, Cristian Consonni, Alberto Montresor
    PLOS ONE, 2021.
    [paper][code]

  8. Pyglmnet: Python implementation of elastic-net regularized generalized linear models
    Mainak Jas, Titipat Achakulvisut, Aid Idrizović, Daniel Acuna, Matthew Antalek, Vinicius Marques, Tommy Odland, Ravi Prakash Garg, Mayank Agrawal, Yu Umegaki, Peter Foley, Hugo Fernandes, Drew Harris, Beibin Li, Olivier Pieters, Scott Otterson, Giovanni De Toni, Chris Rodgers, Eva Dyer, Matti Hamalainen, Konrad Kording, Pavan Ramkumar
    Journal of Open Source Software (JOSS), 2020.
    [paper][code]

Teaching